Artificial-intelligence-based determination of relative positions of objects in medical images

Abstract

Methods and systems are described which allow a classification of first and second objects in an X-ray projection image. A respective representation and localization of both objects are determined by applying the models to match the objects in the X-ray image and a spatial relation of the classified objects is obtained. Such methods and systems take advantage of artificial intelligence.

What is claimed is: 
     
         1 . A method comprising:
 receiving a first X-ray projection image generated by an X-ray imaging device at a first position providing a first view onto an anatomy;   classifying at least a first part of a first object in the first X-ray projection image;   receiving a first model of the first object;   determining a representation of at least the first part of the first object and a first localization of the first object with respect to a coordinate system, by applying the first model to match at least the first part of the first object in the first X-ray image;   moving the X-ray imaging device from the first position to a second position,   receiving a second X-ray projection image generated by the X-ray imaging device at the second position providing a second view onto the anatomy; and   registering the first and second X-ray images, wherein the method comprising accounting for the movement of the X-ray imaging device between the generation of the received first X-ray image and the generation of the second X-ray images when registering the first and second X-ray images.   
     
     
         2 . The method of  claim 1 , wherein the X-ray imaging device is moved translationally from the first position to the second position. 
     
     
         3 . The method of  claim 1 , wherein the anatomical area that is depicted in the first X-ray projection image does not overlap with the anatomical area that is depicted in the second X-ray projection image. 
     
     
         4 . The method of  claim 1 , comprising classifying at least a second part of the first object in the second X-ray projection image;
 determining a representation of at least the second part of the first object and a second localization of the first object with respect to the coordinate system, by applying the first model to match at least the second part of the first object in the second X-ray projection image.   
     
     
         5 . The method of  claim 1 , comprising classifying a second object in the second X-ray projection image;
 receiving a second model of the second object;   determining a representation of at least a part of the second object and a second localization of the second object, by applying the second model of the second object to match at least the part of the second object in the second X-ray projection image; and   determining a spatial relation of the first and second objects.   
     
     
         6 . The method of  claim 1 , comprising moving the X-ray imaging device to a third position, receiving a third X-ray projection image generated by the X-ray imaging device at the third position providing a third view onto the anatomy;
 classifying at least the first part of the first object in the third X-ray projection image;   determining the representation of at least the first part of the first object and a third localization of the first object with respect to the coordinate system, by applying the first model to match at least the first part of the first object in the third X-ray image;   registering the third X-ray projection image with at least one of the first and second X-ray images,   
     
     
         7 . The method of  claim 1 , wherein an amount of the movement of the X-ray imaging device is measured by sensors at the X-ray imaging device. 
     
     
         8 . The method of  claim 1 , wherein each of the X-ray projection images comprises an image characteristic from a group including a pillow effect, a curvature, noise, distortion or a combination thereof, the method further comprising accounting for the image characteristic when matching the first model with the first object. 
     
     
         9 . The method of  claim 1 , further comprising detecting an exchange of the positions of X-ray source and X-ray receiver. 
     
     
         10 . A system comprising a processing unit configured to execute a computer program product including sets of instructions causing the system to perform the following method:
 receiving a first X-ray projection image generated by an X-ray imaging device at a first position providing a first view onto an anatomy;   classifying at least a first part of a first object in the first X-ray projection image;   receiving a first model of the first object;   determining a representation of at least the first part of the first object and a first localization of the first object with respect to a coordinate system, by applying the first model to match at least the first part of the first object in the first X-ray image;   moving the X-ray imaging device from the first position to a second position,   receiving a second X-ray projection image generated by the X-ray imaging device at the second position providing a second view onto the anatomy; and   registering the first and second X-ray images, wherein the method comprising accounting for the movement of the X-ray imaging device between the generation of the received first X-ray image and the generation of the second X-ray images when registering the first and second X-ray images.   
     
     
         11 . The system of  claim 10 , further comprising an X-ray imaging device, wherein the X-ray imaging device is at least one of translationally and rotationally movable from the first position to the second position. 
     
     
         12 . The system of  claim 10 , further comprising a database. 
     
     
         13 . A non-transitory computer readable medium comprising processor-executable instructions for reading data from a processor in communication with an X-ray imaging device, the processor-executable instructions when executed on the processor in a device configure the device to:
 receive a first X-ray projection image generated by an X-ray imaging device at a first position providing a first view onto an anatomy;   classify at least a first part of a first object in the first X-ray projection image;   receive a first model of the first object;   determine a representation of at least the first part of the first object and a first localization of the first object with respect to a coordinate system, by applying the first model to match at least the first part of the first object in the first X-ray image;   move the X-ray imaging device from the first position to a second position,   receive a second X-ray projection image generated by the X-ray imaging device at the second position providing a second view onto the anatomy; and   
       register the first and second X-ray images, wherein the method comprising accounting for the movement of the X-ray imaging device between the generation of the received first X-ray image and the generation of the second X-ray images when registering the first and second X-ray images.